1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
|
; RUN: opt -passes='print<access-info>' -disable-output < %s 2>&1 | FileCheck %s
; We give up analyzing the dependences in this loop due to non-constant
; distance between A[i+offset] and A[i] and add memchecks to prove
; independence. Make sure that no dependences are reported in
; this case.
;
; for (i = 0; i < n; i++)
; A[i + offset] = A[i] * B[i] * C[i];
target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-apple-macosx10.10.0"
; CHECK: Memory dependences are safe with run-time checks
; CHECK-NEXT: Dependences:
; CHECK-NEXT: Run-time memory checks:
; CHECK-NEXT: 0:
; CHECK-NEXT: Comparing group
; CHECK-NEXT: %arrayidxA2 = getelementptr inbounds i16, ptr %a, i64 %idx
; CHECK-NEXT: Against group
; CHECK-NEXT: %arrayidxA = getelementptr inbounds i16, ptr %a, i64 %indvar
@B = common global ptr null, align 8
@A = common global ptr null, align 8
@C = common global ptr null, align 8
define void @f(i64 %offset) {
entry:
%a = load ptr, ptr @A, align 8
%b = load ptr, ptr @B, align 8
%c = load ptr, ptr @C, align 8
br label %for.body
for.body: ; preds = %for.body, %entry
%indvar = phi i64 [ 0, %entry ], [ %add, %for.body ]
%arrayidxA = getelementptr inbounds i16, ptr %a, i64 %indvar
%loadA = load i16, ptr %arrayidxA, align 2
%arrayidxB = getelementptr inbounds i16, ptr %b, i64 %indvar
%loadB = load i16, ptr %arrayidxB, align 2
%arrayidxC = getelementptr inbounds i16, ptr %c, i64 %indvar
%loadC = load i16, ptr %arrayidxC, align 2
%mul = mul i16 %loadB, %loadA
%mul1 = mul i16 %mul, %loadC
%idx = add i64 %indvar, %offset
%arrayidxA2 = getelementptr inbounds i16, ptr %a, i64 %idx
store i16 %mul1, ptr %arrayidxA2, align 2
%add = add nuw nsw i64 %indvar, 1
%exitcond = icmp eq i64 %add, 20
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|
